Exposure to Operative Anesthesia in Childhood and Subsequent Neurobehavioral Diagnoses: A Natural Experiment using Appendectomy

BACKGROUND

Observational studies of anesthetic neurotoxicity may be biased because children requiring anesthesia commonly have medical conditions associated with neurobehavioral problems. This study takes advantage of a natural experiment associated with appendicitis, in order to determine if anesthesia and surgery in childhood were specifically associated with subsequent neurobehavioral outcomes.

METHODS

We identified 134,388 healthy children with appendectomy and examined the incidence of subsequent externalizing or behavioral disorders (conduct, impulse control, oppositional defiant, or attention-deficit/hyperactivity disorder); or internalizing or mood/anxiety disorders (depression, anxiety, or bipolar disorder) when compared to 671,940 matched healthy controls as identified in Medicaid data between 2001-2018. For comparison, we also examined 154,887 otherwise healthy children admitted to the hospital for pneumonia, cellulitis, and gastroenteritis, of which only 8% received anesthesia, and compared them to 774,435 matched healthy controls. We also examined the difference-in-differences between matched appendectomy patients and their controls and matched medical admission patients and their controls.

RESULTS

Compared to controls, children with appendectomy were more likely to have subsequent behavioral disorders (the hazard ratio (HR) was 1.04 (95% CI 1.01, 1.06), P = 0.0010), and mood/anxiety disorders (HR: 1.15 (95% CI 1.13, 1.17), P < 0.0001). Relative to controls, children with medical admissions were also more likely to have subsequent behavioral (HR: 1.20 (95% CI 1.18, 1.22), P < 0.0001), and mood/anxiety (HR: 1.25 (95% CI 1.23, 1.27), P < 0.0001) disorders. Comparing the difference between matched appendectomy patients and their matched controls to the difference between matched medical patients and their matched controls, medical patients had more subsequent neurobehavioral problems than appendectomy patients.

CONCLUSIONS

Although there is an association between neurobehavioral diagnoses and appendectomy, this association is not specific to anesthesia exposure, and is stronger in medical admissions. Medical admissions, generally without anesthesia exposure, displayed significantly higher rates of these disorders than appendectomy-exposed patients.

Mortality Among Older Medical Patients at Flagship Hospitals and Their Affiliates

BACKGROUND

We define a "flagship hospital" as the largest academic hospital within a hospital referral region and a "flagship system" as a system that contains a flagship hospital and its affiliates. It is not known if patients admitted to an affiliate hospital, and not to its main flagship hospital, have better outcomes than those admitted to a hospital outside the flagship system but within the same hospital referral region.

OBJECTIVE

To compare mortality at flagship hospitals and their affiliates to matched control patients not in the flagship system but within the same hospital referral region.

DESIGN

A matched cohort study PARTICIPANTS: The study used hospitalizations for common medical conditions between 2018-2019 among older patients age ≥ 66 years. We analyzed 118,321 matched pairs of Medicare patients admitted with pneumonia (N=57,775), heart failure (N=42,531), or acute myocardial infarction (N=18,015) in 35 flagship hospitals, 124 affiliates, and 793 control hospitals.

MAIN MEASURES

30-day (primary) and 90-day (secondary) all-cause mortality.

KEY RESULTS

30-day mortality was lower among patients in flagship systems versus control hospitals that are not part of the flagship system but within the same hospital referral region (difference= -0.62%, 95% CI [-0.88%, -0.37%], P<0.001). This difference was smaller in affiliates versus controls (-0.43%, [-0.75%, -0.11%], P=0.008) than in flagship hospitals versus controls (-1.02%, [-1.46%, -0.58%], P<0.001; difference-in-difference -0.59%, [-1.13%, -0.05%], P=0.033). Similar results were found for 90-day mortality.

LIMITATIONS

The study used claims-based data.

CONCLUSIONS

In aggregate, within a hospital referral region, patients treated at the flagship hospital, at affiliates of the flagship hospital, and in the flagship system as a whole, all had lower mortality rates than matched controls outside the flagship system. However, the mortality advantage was larger for flagship hospitals than for their affiliates.

Impact of Hospital Affiliation With a Flagship Hospital System on Surgical Outcomes

OBJECTIVE

To compare general surgery outcomes at flagship systems, flagship hospitals, and flagship hospital affiliates versus matched controls.

SUMMARY BACKGROUND DATA

It is unknown whether flagship hospitals perform better than flagship hospital affiliates for surgical patients.

METHODS

Using Medicare claims for 2018 to 2019, we matched patients undergoing inpatient general surgery in flagship system hospitals to controls who underwent the same procedure at hospitals outside the system but within the same region. We defined a "flagship hospital" within each region as the major teaching hospital with the highest patient volume that is also part of a hospital system; its system was labeled a "flagship system." We performed 4 main comparisons: patients treated at any flagship system hospital versus hospitals outside the flagship system; flagship hospitals versus hospitals outside the flagship system; flagship hospital affiliates versus hospitals outside the flagship system; and flagship hospitals versus affiliate hospitals. Our primary outcome was 30-day mortality.

RESULTS

We formed 32,228 closely matched pairs across 35 regions. Patients at flagship system hospitals (32,228 pairs) had lower 30-day mortality than matched control patients [3.79% vs. 4.36%, difference=-0.57% (-0.86%, -0.28%), P<0.001]. Similarly, patients at flagship hospitals (15,571/32,228 pairs) had lower mortality than control patients. However, patients at flagship hospital affiliates (16,657/32,228 pairs) had similar mortality to matched controls. Flagship hospitals had lower mortality than affiliate hospitals [difference-in-differences=-1.05% (-1.62%, -0.47%), P<0.001].

CONCLUSIONS

Patients treated at flagship hospitals had significantly lower mortality rates than those treated at flagship hospital affiliates. Hence, flagship system affiliation does not alone imply better surgical outcomes.

Assessing the Ambulatory Surgery Center Volume-Outcome Association

Importance

In surgical patients, it is well known that higher hospital procedure volume is associated with better outcomes. To our knowledge, this volume-outcome association has not been studied in ambulatory surgery centers (ASCs) in the US.

Objective

To determine if low-volume ASCs have a higher rate of revisits after surgery, particularly among patients with multimorbidity.

Design, Setting, and Participants

This matched case-control study used Medicare claims data and analyzed surgeries performed during 2018 and 2019 at ASCs. The study examined 2328 ASCs performing common ambulatory procedures and analyzed 4751 patients with a revisit within 7 days of surgery (defined to be either 1 of 4735 revisits or 1 of 16 deaths without a revisit). These cases were each closely matched to 5 control patients without revisits (23 755 controls). Data were analyzed from January 1, 2018, through December 31, 2019.

Main Outcomes and Measures

Seven-day revisit in patients (cases) compared with the matched patients without the outcome (controls) in ASCs with low volume (less than 50 procedures over 2 years) vs higher volume (50 or more procedures).

Results

Patients at a low-volume ASC had a higher odds of a 7-day revisit vs patients who had their surgery at a higher-volume ASC (odds ratio [OR], 1.21; 95% CI, 1.09-1.36; P = .001). The odds of revisit for patients with multimorbidity were higher at low-volume ASCs when compared with higher-volume ASCs (OR, 1.57; 95% CI, 1.27-1.94; P < .001). Among patients with multimorbidity in low-volume ASCs, for those who underwent orthopedic procedures, the odds of revisit were 84% higher (OR, 1.84; 95% CI, 1.36-2.50; P < .001) vs higher-volume centers, and for those who underwent general surgery or other procedures, the odds of revisit were 36% higher (OR, 1.36; 95% CI, 1.01-1.83; P = .05) vs a higher-volume center. The findings were not statistically significant for patients without multimorbidity.

Conclusions and Relevance

In this observational study, the surgical volume of an ASC was an important indicator of patient outcomes. Older patients with multimorbidity should discuss with their surgeon the optimal location of their care.

A second evidence factor for a second control group

In an observational study of the effects caused by a treatment, a second control group is used in an effort to detect bias from unmeasured covariates, and the investigator is content if no evidence of bias is found. This strategy is not entirely satisfactory: two control groups may differ significantly, yet the difference may be too small to invalidate inferences about the treatment, or the control groups may not differ yet nonetheless fail to provide a tangible strengthening of the evidence of a treatment effect. Is a firmer conclusion possible? Is there a way to analyze a second control group such that the data might report measurably strengthened evidence of cause and effect, that is, insensitivity to larger unmeasured biases? Evidence factor analyses are not commonly used with a second control group: most analyses compare the treated group to each control group, but analyses of that kind are partially redundant; so, they do not constitute evidence factors. An alternative analysis is proposed here, one that does yield two evidence factors, and with a carefully designed test statistic, is capable of extracting strong evidence from the second factor. The new technical work here concerns the development of a test statistic with high design sensitivity and high Bahadur efficiency in a sensitivity analysis for the second factor. A study of binge drinking as a cause of high blood pressure is used as an illustration.

Explaining racial disparities in surgical survival: a tapered match analysis of patient and hospital factors

OBJECTIVES

Evaluate whether hospital factors, including nurse resources, explain racial differences in Medicare black and white patient surgical outcomes and whether disparities changed over time.

DESIGN

Retrospective tapered-match.

SETTING

571 hospitals at two time points (Early Era 2003-2005; Recent Era 2013-2015).

PARTICIPANTS

6752 black patients and three sets of 6752 white controls selected from 107 001 potential controls (Early Era). 4964 black patients and three sets of 4964 white controls selected from 74 108 potential controls (Recent Era).

INTERVENTIONS

Black patients were matched to white controls on demographics (age, sex, state and year of procedure), procedure (demographics variables plus 136 International Classification of Diseases (ICD)-9 principal procedure codes) and presentation (demographics and procedure variables plus 34 comorbidities, a mortality risk score, a propensity score for being black, emergency admission, transfer status, predicted procedure time).

OUTCOMES

30-day and 1-year mortality.

RESULTS

Before matching, black patients had more comorbidities, higher risk of mortality despite being younger and underwent procedures at different percentages than white patients. Whites in the demographics match had lower mortality at 30 days (5.6% vs 6.7% Early Era; 5.4% vs 5.7% Recent Era) and 1-year (15.5% vs 21.5% Early Era; 12.3% vs 15.9% Recent Era). Black-white 1-year mortality differences were equivalent after matching patients with respect to presentation, procedure and demographic factors. Black-white 30-day mortality differences were equivalent after matching on procedure and demographic factors. Racial disparities in outcomes remained unchanged between the two time periods spanning 10 years. All patients in hospitals with better nurse resources had lower odds of 30-day (OR 0.60, 95% CI 0.46 to 0.78, p<0.010) and 1-year mortality (OR 0.77, 95% CI 0.65 to 0.92, p<0.010) even after accounting for other hospital factors.

CONCLUSIONS

Survival disparities among black and white patients are largely explained by differences in demographic, procedure and presentation factors. Better nurse resources (eg, staffing, work environment) were associated with lower mortality for all patients.

Defining Multimorbidity in Older Patients Hospitalized with Medical Conditions

BACKGROUND

The term "multimorbidity" identifies high-risk, complex patients and is conventionally defined as ≥2 comorbidities. However, this labels almost all older patients as multimorbid, making this definition less useful for physicians, hospitals, and policymakers.

OBJECTIVE

Develop new medical condition-specific multimorbidity definitions for patients admitted with acute myocardial infarction (AMI), heart failure (HF), and pneumonia patients. We developed three medical condition-specific multimorbidity definitions as the presence of single, double, or triple combinations of comorbidities - called Qualifying Comorbidity Sets (QCSs) - associated with at least doubling the risk of 30-day mortality for AMI and pneumonia, or one-and-a-half times for HF patients, compared to typical patients with these conditions.

DESIGN

Cohort-based matching study PARTICIPANTS: One hundred percent Medicare Fee-for-Service beneficiaries with inpatient admissions between 2016 and 2019 for AMI, HF, and pneumonia.

MAIN MEASURES

Thirty-day all-location mortality KEY RESULTS: We defined multimorbidity as the presence of ≥1 QCS. The new definitions labeled fewer patients as multimorbid with a much higher risk of death compared to the conventional definition (≥2 comorbidities). The proportions of patients labeled as multimorbid using the new definition versus the conventional definition were: for AMI 47% versus 87% (p value<0.0001), HF 53% versus 98% (p value<0.0001), and pneumonia 57% versus 91% (p value<0.0001). Thirty-day mortality was higher among patients with ≥1 QCS compared to ≥2 comorbidities: for AMI 15.0% versus 9.5% (p<0.0001), HF 9.9% versus 7.0% (p <0.0001), and pneumonia 18.4% versus 13.2% (p <0.0001).

CONCLUSION

The presence of ≥2 comorbidities identified almost all patients as multimorbid. In contrast, our new QCS-based definitions selected more specific combinations of comorbidities associated with substantial excess risk in older patients admitted for AMI, HF, and pneumonia. Thus, our new definitions offer a better approach to identifying multimorbid patients, allowing physicians, hospitals, and policymakers to more effectively use such information to consider focused interventions for these vulnerable patients.

Redefining Multimorbidity in Older Surgical Patients

BACKGROUND

Multimorbidity in surgery is common and associated with worse postoperative outcomes. However, conventional multimorbidity definitions (≥2 comorbidities) label the vast majority of older patients as multimorbid, limiting clinical usefulness. We sought to develop and validate better surgical specialty-specific multimorbidity definitions based on distinct comorbidity combinations.

STUDY DESIGN

We used Medicare claims for patients aged 66 to 90 years undergoing inpatient general, orthopaedic, or vascular surgery. Using 2016 to 2017 data, we identified all comorbidity combinations associated with at least 2-fold (general/orthopaedic) or 1.5-fold (vascular) greater risk of 30-day mortality compared with the overall population undergoing the same procedure; we called these combinations qualifying comorbidity sets. We applied them to 2018 to 2019 data (general = 230,410 patients, orthopaedic = 778,131 patients, vascular = 146,570 patients) to obtain 30-day mortality estimates. For further validation, we tested whether multimorbidity status was associated with differential outcomes for patients at better-resourced (based on nursing skill-mix, surgical volume, teaching status) hospitals vs all other hospitals using multivariate matching.

RESULTS

Compared with conventional multimorbidity definitions, the new definitions labeled far fewer patients as multimorbid: general = 85.0% (conventional) vs 55.9% (new) (p < 0.0001); orthopaedic = 66.6% vs 40.2% (p < 0.0001); and vascular = 96.2% vs 52.7% (p < 0.0001). Thirty-day mortality was higher by the new definitions: general = 3.96% (conventional) vs 5.64% (new) (p < 0.0001); orthopaedic = 0.13% vs 1.68% (p < 0.0001); and vascular = 4.43% vs 7.00% (p < 0.0001). Better-resourced hospitals offered significantly larger mortality benefits than all other hospitals for multimorbid vs nonmultimorbid general and orthopaedic, but not vascular, patients (general surgery difference-in-difference = -0.94% [-1.36%, -0.52%], p < 0.0001; orthopaedic = -0.20% [-0.34%, -0.05%], p = 0.0087; and vascular = -0.12% [-0.69%, 0.45%], p = 0.6795).

CONCLUSIONS

Our new multimorbidity definitions identified far more specific, higher-risk pools of patients than conventional definitions, potentially aiding clinical decision-making.

The Safety of Performing Surgery at Ambulatory Surgery Centers Versus Hospital Outpatient Departments in Older Patients With or Without Multimorbidity

BACKGROUND

Surgery for older Americans is increasingly being performed at ambulatory surgery centers (ASCs) rather than hospital outpatient departments (HOPDs), while rates of multimorbidity have increased.

OBJECTIVE

To determine whether there are differential outcomes in older patients undergoing surgical procedures at ASCs versus HOPDs.

RESEARCH DESIGN

Matched cohort study.

SUBJECTS

Of Medicare patients, 30,958 were treated in 2018 and 2019 at an ASC undergoing herniorrhaphy, cholecystectomy, or open breast procedures, matched to similar HOPD patients, and another 32,702 matched pairs undergoing higher-risk procedures.

MEASURES

Seven and 30-day revisit and complication rates.

RESULTS

For the same procedures, HOPD patients displayed a higher baseline predicted risk of 30-day revisits than ASC patients (13.09% vs 8.47%, P < 0.0001), suggesting the presence of considerable selection on the part of surgeons. In matched Medicare patients with or without multimorbidity, we observed worse outcomes in HOPD patients: 30-day revisit rates were 8.1% in HOPD patients versus 6.2% in ASC patients ( P < 0.0001), and complication rates were 41.3% versus 28.8%, P < 0.0001. Similar patterns were also found for 7-day outcomes and in higher-risk procedures examined in a secondary analysis. Similar patterns were also observed when analyzing patients with and without multimorbidity separately.

CONCLUSIONS

The rates of revisits and complications for ASC patients were far lower than for closely matched HOPD patients. The observed initial baseline risk in HOPD patients was much higher than the baseline risk for the same procedures performed at the ASC, suggesting that surgeons are appropriately selecting their riskier patients to be treated at the HOPD rather than the ASC.

Sensitivity analyses informed by tests for bias in observational studies

In an observational study, the treatment received and the outcome exhibited may be associated in the absence of an effect caused by the treatment, even after controlling for observed covariates. Two tactics are common: (i) a test for unmeasured bias may be obtained using a secondary outcome for which the effect is known and (ii) a sensitivity analysis may explore the magnitude of unmeasured bias that would need to be present to explain the observed association as something other than an effect caused by the treatment. Can such a test for unmeasured bias inform the sensitivity analysis? If the test for bias does not discover evidence of unmeasured bias, then ask: Are conclusions therefore insensitive to larger unmeasured biases? Conversely, if the test for bias does find evidence of bias, then ask: What does that imply about sensitivity to biases? This problem is formulated in a new way as a convex quadratically constrained quadratic program and solved on a large scale using interior point methods by a modern solver. That is, a convex quadratic function of N variables is minimized subject to constraints on linear and convex quadratic functions of these variables. The quadratic function that is minimized is a statistic for the primary outcome that is a function of the unknown treatment assignment probabilities. The quadratic function that constrains this minimization is a statistic for subsidiary outcome that is also a function of these same unknown treatment assignment probabilities. In effect, the first statistic is minimized over a confidence set for the unknown treatment assignment probabilities supplied by the unaffected outcome. This process avoids the mistake of interpreting the failure to reject a hypothesis as support for the truth of that hypothesis. The method is illustrated by a study of the effects of light daily alcohol consumption on high-density lipoprotein (HDL) cholesterol levels. In this study, the method quickly optimizes a nonlinear function of N = 800 $N=800$ variables subject to linear and quadratic constraints. In the example, strong evidence of unmeasured bias is found using the subsidiary outcome, but, perhaps surprisingly, this finding makes the primary comparison insensitive to larger biases.

Using natural strata when examining unmeasured biases in an observational study of neurological side effects of antibiotics

Fluoroquinolones are widely prescribed antibiotics that carry a US Food and Drug Administration warning about possible side-effects on the central and peripheral nervous system. We compare 436,891 patients with sinusitis treated with fluoroquinolones to two control groups treated with azithromycin or amoxicillin. In addition to looking for nervous system complications, we look for evidence of bias using outcomes for which an effect was not anticipated. The comparison uses ‘natural strata’ that form control groups proportional in size to the treated group and balance many covariates beyond those that define the strata. The main technical contribution is a new method for near-optimal construction of natural strata with multiple groups. The online supplement material contains proofs, details, and information about the R package natstrat and replication.

Alzheimer's Dementia After Exposure to Anesthesia and Surgery in the Elderly: A Matched Natural Experiment Using Appendicitis

OBJECTIVE

The aim of this study was to determine whether surgery and anesthesia in the elderly may promote Alzheimer disease and related dementias (ADRD).

BACKGROUND

There is a substantial conflicting literature concerning the hypothesis that surgery and anesthesia promotes ADRD. Much of the literature is confounded by indications for surgery or has small sample size. This study examines elderly patients with appendicitis, a common condition that strikes mostly at random after controlling for some known associations.

METHODS

A matched natural experiment of patients undergoing appendectomy for appendicitis versus control patients without appendicitis using Medicare data from 2002 to 2017, examining 54,996 patients without previous diagnoses of ADRD, cognitive impairment, or neurological degeneration, who developed appendicitis between ages 68 through 77 years and underwent an appendectomy (the ''Appendectomy'' treated group), matching them 5:1 to 274,980 controls, examining the subsequent hazard for developing ADRD.

RESULTS

The hazard ratio (HR) for developing ADRD or death was lower in the Appendectomy group than controls: HR = 0.96 [95% confidence interval (CI) 0.94-0.98], P < 0.0001, (28.2% in Appendectomy vs 29.1% in controls, at 7.5 years). The HR for death was 0.97 (95% CI 0.95-0.99), P = 0.002, (22.7% vs 23.1% at 7.5 years). The HR for developing ADRD alone was 0.89 (95% CI 0.86-0.92), P < 0.0001, (7.6% in Appendectomy vs 8.6% in controls, at 7.5 years). No subgroup analyses found significantly elevated rates of ADRD in the Appendectomy group.

CONCLUSION

In this natural experiment involving 329,976 elderly patients, exposure to appendectomy surgery and anesthesia did not increase the subsequent rate of ADRD.

Propensity Scores in the Design of Observational Studies for Causal Effects

The design of any study, whether experimental or observational, that is intended to estimate the causal effects of a treatment condition relative to a control condition, refers to those activities that precede any examination of outcome variables. As defined in our 1983 article (Rosenbaum & Rubin, 1983), the propensity score is the unit-level conditional probability of assignment to treatment versus control given the observed covariates; so, the propensity score explicitly does not involve any outcome variables, in contrast to other summaries of variables sometimes used in observational studies. Balancing the distributions of covariates in the treatment and control groups by matching or balancing on the propensity score is therefore an aspect of the design of the observational study. In this invited comment on our 1983 article, we review the situation in the early 1980’s, and we recall some apparent paradoxes that propensity scores helped to resolve. We demonstrate that it is possible to balance an enormous number of low-dimensional summaries of a high-dimensional covariate, even though it is generally impossible to match individuals closely for all of the components of a high-dimensional covariate. In a sense, there is only one crucial observed covariate, the propensity score, and there is one crucial unobserved covariate, the ‘principal unobserved covariate’. The propensity score and the principal unobserved covariate are equal when treatment assignment is strongly ignorable, that is, unconfounded. Controlling for observed covariates is a prelude to the crucial step from association to causation, the step that addresses potential biases from unmeasured covariates. The design of an observational study also prepares for the step to causation: by selecting comparisons to increase the design sensitivity, by seeking opportunities to detect bias, by seeking mutually supportive evidence affected by different biases, by incorporating quasi-experimental devices such as multiple control groups, and by including the economist’s instruments. All of these considerations reflect the formal development of sensitivity analyses that were largely informal prior to the 1980s.

A statistic with demonstrated insensitivity to unmeasured bias for 2 × 2 × S tables in observational studies

Are weak associations between a treatment and a binary outcome always sensitive to small unmeasured biases in observational studies? This possibility is often discussed in epidemiology. The familiar Mantel-Haenszel test for a 2 × 2 × S $$ 2\times 2\times S $$ contingency table exaggerates sensitivity to unmeasured biases when the population odds ratios vary among the S $$ S $$ strata. A statistic built from several components, here from the S $$ S $$  strata, is said to have demonstrated insensitivity to bias if it uses only those components that provide indications of insensitivity to bias. Briefly, such a statistic is a d $$ d $$ -statistic. There are 2 S - 1 $$ {2}^S-1 $$ candidate statistics with S $$ S $$ strata, and a d $$ d $$ -statistic considers them all.  To have level α $$ \alpha $$ , a test based on a d $$ d $$ -statistic must pay a price for its double use of the data, but as the sample size increases, that price becomes small, while the gain may be large. The price is paid by conditioning on the limited information used to identify components that are insensitive to a bias of specified magnitude, basing the test result on the information that remains after conditioning. In large samples, the d $$ d $$ -statistic achieves the largest possible design sensitivity, so it does not exaggerate sensitivity to unmeasured bias. A simulation verifies that the large sample result has traction in samples of practical size. A study of sunlight as a cause of cataract is used to illustrate issues and methods. Several extensions of the method are discussed. An R package dstat2x2xk implements the method.

Matching One Sample According to Two Criteria in Observational Studies

Multivariate matching has two goals: (i) to construct treated and control groups that have similar distributions of observed covariates, and (ii) to produce matched pairs or sets that are homogeneous in a few key covariates. When there are only a few binary covariates, both goals may be achieved by matching exactly for these few covariates. Commonly, however, there are many covariates, so goals (i) and (ii) come apart, and must be achieved by different means. As is also true in a randomized experiment, similar distributions can be achieved for a high-dimensional covariate, but close pairs can be achieved for only a few covariates. We introduce a new polynomial-time method for achieving both goals that substantially generalizes several existing methods; in particular, it can minimize the earthmover distance between two marginal distributions. The method involves minimum cost flow optimization in a network built around a tripartite graph, unlike the usual network built around a bipartite graph. In the tripartite graph, treated subjects appear twice, on the far left and the far right, with controls sandwiched between them, and efforts to balance covariates are represented on the right, while efforts to find close individual pairs are represented on the left. In this way, the two efforts may be pursued simultaneously without conflict. The method is applied to our on-going study in the Medicare population of the relationship between superior nursing and sepsis mortality. The match2C package in R implements the method.

A National Comparison of Operative Outcomes of New and Experienced Surgeons

OBJECTIVE

To determine whether outcomes achieved by new surgeons are attributable to inexperience or to differences in the context in which care is delivered and patient complexity.

BACKGROUND

Although prior studies suggest that new surgeon outcomes are worse than those of experienced surgeons, factors that underlie these phenomena are poorly understood.

METHODS

A nationwide observational tapered matching study of outcomes of Medicare patients treated by new and experienced surgeons in 1221 US hospitals (2009-2013). The primary outcome studied is 30-day mortality. Secondary outcomes were examined.

RESULTS

In total, 694,165 patients treated by 8503 experienced surgeons were matched to 68,036 patients treated by 2119 new surgeons working in the same hospitals. New surgeons' patients were older (25.8% aged ≥85 vs 16.3%,P<0.0001) with more emergency admissions (53.9% vs 25.8%,P<0.0001) than experienced surgeons' patients. Patients of new surgeons had a significantly higher baseline 30-day mortality rate compared with patients of experienced surgeons (6.2% vs 4.5%,P<0.0001;OR 1.42 (1.33, 1.52)). The difference remained significant after matching the types of operations performed (6.2% vs 5.1%, P<0.0001; OR 1.24 (1.16, 1.32)) and after further matching on a combination of operation type and emergency admission status (6.2% vs 5.6%, P=0.0007; OR 1.12 (1.05, 1.19)). After matching on operation type, emergency admission status, and patient complexity, the difference between new and experienced surgeons' patients' 30-day mortality became indistinguishable (6.2% vs 5.9%,P=0.2391;OR 1.06 (0.97, 1.16)).

CONCLUSIONS

Among Medicare beneficiaries, the majority of the differences in outcomes between new and experienced surgeons are related to the context in which care is delivered and patient complexity rather than new surgeon inexperience.

Evaluating the Costs and Outcomes of Hospital Nursing Resources: a Matched Cohort Study of Patients with Common Medical Conditions

BACKGROUND

Nursing resources, such as staffing ratios and skill mix, vary across hospitals. Better nursing resources have been linked to better patient outcomes but are assumed to increase costs. The value of investments in nursing resources, in terms of clinical benefits relative to costs, is unclear.

OBJECTIVE

To determine whether there are differential clinical outcomes, costs, and value among medical patients at hospitals characterized by better or worse nursing resources.

DESIGN

Matched cohort study of patients in 306 acute care hospitals.

PATIENTS

A total of 74,045 matched pairs of fee-for-service Medicare beneficiaries admitted for common medical conditions (25,446 sepsis pairs; 16,332 congestive heart failure pairs; 12,811 pneumonia pairs; 10,598 stroke pairs; 8858 acute myocardial infarction pairs). Patients were also matched on hospital size, technology, and teaching status.

MAIN MEASURES

Better (n = 76) and worse (n = 230) nursing resourced hospitals were defined by patient-to-nurse ratios, skill mix, proportions of bachelors-degree nurses, and nurse work environments. Outcomes included 30-day mortality, readmission, and resource utilization-based costs.

KEY RESULTS

Patients in hospitals with better nursing resources had significantly lower 30-day mortality (16.1% vs 17.1%, p < 0.0001) and fewer readmissions (32.3% vs 33.6%, p < 0.0001) yet costs were not significantly different ($18,848 vs 18,671, p = 0.133). The greatest outcomes and cost advantage of better nursing resourced hospitals were in patients with sepsis who had lower mortality (25.3% vs 27.6%, p < 0.0001). Overall, patients with the highest risk of mortality on admission experienced the greatest reductions in mortality and readmission from better nursing at no difference in cost.

CONCLUSIONS

Medicare beneficiaries with common medical conditions admitted to hospitals with better nursing resources experienced more favorable outcomes at almost no difference in cost.

Using Medicare claims in identifying Alzheimer's disease and related dementias

INTRODUCTION

This study develops a measure of Alzheimer's disease and related dementias (ADRD) using Medicare claims.

METHODS

Validation resembles the approach of the American Psychological Association, including (1) content validity, (2) construct validity, and (3) predictive validity.

RESULTS

We found that four items-a Medicare claim recording ADRD 1 year ago, 2 years ago, 3 years ago, and a total stay of 6 months in a nursing home-exhibit a pattern of association consistent with a single underlying ADRD construct, and presence of any two of these four items predict a direct measure of cognitive function and also future claims for ADRD.

DISCUSSION

Our four items are internally consistent with the measurement of a single quantity. The presence of any two items do a better job than a single claim when predicting both a direct measure of cognitive function and future ADRD claims.

Combining planned and discovered comparisons in observational studies

In observational studies of treatment effects, it is common to have several outcomes, perhaps of uncertain quality and relevance, each purporting to measure the effect of the treatment. A single planned combination of several outcomes may increase both power and insensitivity to unmeasured bias when the plan is wisely chosen, but it may miss opportunities in other cases. A method is proposed that uses one planned combination with only a mild correction for multiple testing and exhaustive consideration of all possible combinations fully correcting for multiple testing. The method works with the joint distribution of $\kappa^{T}\left( \mathbf{T}-\boldsymbol{\mu}\right) /\sqrt {\boldsymbol{\kappa}^{T}\boldsymbol{\Sigma\boldsymbol{\kappa}}}$ and $max_{\boldsymbol{\lambda}\neq\mathbf{0}}$$\,\lambda^{T}\left( \mathbf{T} -\boldsymbol{\mu}\right) /$$\sqrt{\boldsymbol{\lambda}^{T}\boldsymbol{\Sigma \lambda}}$ where $\kappa$ is chosen a priori and the test statistic $\mathbf{T}$ is asymptotically $N_{L}\left( \boldsymbol{\mu},\boldsymbol{\Sigma}\right) $. The correction for multiple testing has a smaller effect on the power of $\kappa^{T}\left( \mathbf{T}-\boldsymbol{\mu }\right) /\sqrt{\boldsymbol{\kappa}^{T}\boldsymbol{\Sigma\boldsymbol{\kappa} }}$ than does switching to a two-tailed test, even though the opposite tail does receive consideration when $\lambda=-\kappa$. In the application, there are three measures of cognitive decline, and the a priori comparison $\kappa$ is their first principal component, computed without reference to treatment assignments. The method is implemented in an R package sensitivitymult.

A conditional test with demonstrated insensitivity to unmeasured bias in matched observational studies

In an observational study matched for observed covariates, an association between treatment received and outcome exhibited may indicate not an effect caused by the treatment, but merely some bias in the allocation of treatments to individuals within matched pairs. The evidence that distinguishes moderate biases from causal effects is unevenly dispersed among possible comparisons in an observational study: some comparisons are insensitive to larger biases than others. Intuitively, larger treatment effects tend to be insensitive to larger unmeasured biases, and perhaps matched pairs can be grouped using covariates, doses or response patterns so that groups of pairs with larger treatment effects may be identified. Even if an investigator has a reasoned conjecture about where to look for insensitive comparisons, that conjecture might prove mistaken, or, when not mistaken, it might be received sceptically by other scientists who doubt the conjecture or judge it to be too convenient in light of its success with the data at hand. In this article a test is proposed that searches for insensitive findings over many comparisons, but controls the probability of falsely rejecting a true null hypothesis of no treatment effect in the presence of a bias of specified magnitude. An example is studied in which the test considers many comparisons and locates an interpretable comparison that is insensitive to larger biases than a conventional comparison based on Wilcoxon’s signed rank statistic applied to all pairs. A simulation examines the power of the proposed test. The method is implemented in the R package dstat, which contains the example and reproduces the analysis.

Valuing hospital investments in nursing: multistate matched-cohort study of surgical patients

BACKGROUND

There are known clinical benefits associated with investments in nursing. Less is known about their value.

AIMS

To compare surgical patient outcomes and costs in hospitals with better versus worse nursing resources and to determine if value differs across these hospitals for patients with different mortality risks.

METHODS

Retrospective matched-cohort design of patient outcomes at hospitals with better versus worse nursing resources, defined by patient-to-nurse ratios, skill mix, proportions of bachelors-degree nurses and nurse work environments. The sample included 62 715 pairs of surgical patients in 76 better nursing resourced hospitals and 230 worse nursing resourced hospitals from 2013 to 2015. Patients were exactly matched on principal procedures and their hospital's size category, teaching and technology status, and were closely matched on comorbidities and other risk factors.

RESULTS

Patients in hospitals with better nursing resources had lower 30-day mortality: 2.7% vs 3.1% (p<0.001), lower failure-to-rescue: 5.4% vs 6.2% (p<0.001), lower readmissions: 12.6% vs 13.5% (p<0.001), shorter lengths of stay: 4.70 days vs 4.76 days (p<0.001), more intensive care unit admissions: 17.2% vs 15.4% (p<0.001) and marginally higher nurse-adjusted costs (which account for the costs of better nursing resources): $20 096 vs $19 358 (p<0.001), as compared with patients in worse nursing resourced hospitals. The nurse-adjusted cost associated with a 1% improvement in mortality at better nursing hospitals was $2035. Patients with the highest mortality risk realised the greatest value from nursing resources.

CONCLUSION

Hospitals with better nursing resources provided better clinical outcomes for surgical patients at a small additional cost. Generally, the sicker the patient, the greater the value at better nursing resourced hospitals.

Using Evidence Factors to Clarify Exposure Biomarkers

A study has 2 evidence factors if it permits 2 statistically independent inferences about 1 treatment effect such that each factor is immune to some bias that would invalidate the other factor. Because the 2 factors are statistically independent, the evidence they provide can be combined using methods associated with meta-analysis for independent studies, despite using the same data twice in different ways. We illustrate evidence factors, applying them in a new way in investigations that have both an exposure biomarker and a coarse external measure of exposure to a treatment. To illustrate, we consider the possible effects of cigarette smoking on homocysteine levels, with self-reported smoking and a cotinine biomarker. We examine joint sensitivity of 2 factors to bias from confounding, a central aspect of any observational study.

Disparities in Breast Cancer Survival by Socioeconomic Status Despite Medicare and Medicaid Insurance

Policy Points Patients with low socioeconomic status (SES) experience poorer survival rates after diagnosis of breast cancer, even when enrolled in Medicare and Medicaid. Most of the difference in survival is due to more advanced cancer on presentation and the general poor health of lower SES patients, while only a very small fraction of the SES disparity is due to differences in cancer treatment. Even when comparing only low- versus not-low-SES whites (without confounding by race) the survival disparity between disparate white SES populations is very large and is associated with lower use of preventive care, despite having insurance.

CONTEXT

Disparities in breast cancer survival by socioeconomic status (SES) exist despite the "safety net" programs Medicare and Medicaid. What is less clear is the extent to which SES disparities affect various racial and ethnic groups and whether causes differ across populations.

METHODS

We conducted a tapered matching study comparing 1,890 low-SES (LSES) non-Hispanic white, 1,824 black, and 723 Hispanic white women to 60,307 not-low-SES (NLSES) non-Hispanic white women, all in Medicare and diagnosed with invasive breast cancer between 1992 and 2010 in 17 US Surveillance, Epidemiology, and End Results (SEER) regions. LSES Medicare patients were Medicaid dual-eligible and resided in neighborhoods with both high poverty and low education. NLSES Medicare patients had none of these factors.

MEASUREMENTS

5-year and median survival.

FINDINGS

LSES non-Hispanic white patients were diagnosed with more stage IV disease (6.6% vs 3.6%; p < 0.0001), larger tumors (24.6 mm vs 20.2 mm; p < 0.0001), and more chronic diseases such as diabetes (37.8% vs 19.0%; p < 0.0001) than NLSES non-Hispanic white patients. Disparity in 5-year survival (NLSES - LSES) was 13.7% (p < 0.0001) when matched for age, year, and SEER site (a 42-month difference in median survival). Additionally, matching 55 presentation factors, including stage, reduced the disparity to 4.9% (p = 0.0012), but further matching on treatments yielded little further change in disparity: 4.6% (p = 0.0014). Survival disparities among LSES blacks and Hispanics, also versus NLSES whites, were significantly associated with presentation factors, though black patients also displayed disparities related to initial treatment. Before being diagnosed, all LSES populations used significantly less preventive care services than matched NLSES controls.

CONCLUSIONS

In Medicare, SES disparities in breast cancer survival were large (even among non-Hispanic whites) and predominantly related to differences of presentation characteristics at diagnosis rather than differences in treatment. Preventive care was less frequent in LSES patients, which may help explain disparities at presentation.

Adjustment for Atherosclerosis Diagnosis Distorts the Effects of Percutaneous Coronary Intervention and the Ranking of Hospital Performance

BACKGROUND

Coronary atherosclerosis raises the risk of acute myocardial infarction (AMI), and is usually included in AMI risk-adjustment models. Percutaneous coronary intervention (PCI) does not cause atherosclerosis, but may contribute to the notation of atherosclerosis in administrative claims. We investigated how adjustment for atherosclerosis affects rankings of hospitals that perform PCI.

METHODS AND RESULTS

This was a retrospective cohort study of 414 715 Medicare beneficiaries hospitalized for AMI between 2009 and 2011. The outcome was 30-day mortality. Regression models determined the association between patient characteristics and mortality. Rankings of the 100 largest PCI and non-PCI hospitals were assessed with and without atherosclerosis adjustment. Patients admitted to PCI hospitals or receiving interventional cardiology more frequently had an atherosclerosis diagnosis. In adjustment models, atherosclerosis was associated, implausibly, with a 42% reduction in odds of mortality (odds ratio=0.58, P<0.0001). Without adjustment for atherosclerosis, the number of expected lives saved by PCI hospitals increased by 62% (P<0.001). Hospital rankings also changed: 72 of the 100 largest PCI hospitals had better ranks without atherosclerosis adjustment, while 77 of the largest non-PCI hospitals had worse ranks (P<0.001).

CONCLUSIONS

Atherosclerosis is almost always noted in patients with AMI who undergo interventional cardiology but less often in medically managed patients, so adjustment for its notation likely removes part of the effect of interventional treatment. Therefore, hospitals performing more extensive imaging and more PCIs have higher atherosclerosis diagnosis rates, making their patients appear healthier and artificially reducing the expected mortality rate against which they are benchmarked. Thus, atherosclerosis adjustment is detrimental to hospitals providing more thorough AMI care.

A powerful approach to the study of moderate effect modification in observational studies

Effect modification means the magnitude or stability of a treatment effect varies as a function of an observed covariate. Generally, larger and more stable treatment effects are insensitive to larger biases from unmeasured covariates, so a causal conclusion may be considerably firmer if this pattern is noted if it occurs. We propose a new strategy, called the submax-method, that combines exploratory, and confirmatory efforts to determine whether there is stronger evidence of causality-that is, greater insensitivity to unmeasured confounding-in some subgroups of individuals. It uses the joint distribution of test statistics that split the data in various ways based on certain observed covariates. For L binary covariates, the method splits the population L times into two subpopulations, perhaps first men and women, perhaps then smokers and nonsmokers, computing a test statistic from each subpopulation, and appends the test statistic for the whole population, making <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mn>2</mml:mn> <mml:mi>L</mml:mi> <mml:mo>+</mml:mo> <mml:mn>1</mml:mn></mml:math> test statistics in total. Although L binary covariates define <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msup><mml:mn>2</mml:mn> <mml:mi>L</mml:mi></mml:msup> </mml:math> interaction groups, only <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mn>2</mml:mn> <mml:mi>L</mml:mi> <mml:mo>+</mml:mo> <mml:mn>1</mml:mn></mml:math> tests are performed, and at least <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>L</mml:mi> <mml:mo>+</mml:mo> <mml:mn>1</mml:mn></mml:math> of these tests use at least half of the data. The submax-method achieves the highest design sensitivity and the highest Bahadur efficiency of its component tests. Moreover, the form of the test is sufficiently tractable that its large sample power may be studied analytically. The simulation suggests that the submax method exhibits superior performance, in comparison with an approach using CART, when there is effect modification of moderate size. Using data from the NHANES I epidemiologic follow-up survey, an observational study of the effects of physical activity on survival is used to illustrate the method. The method is implemented in the <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>R</mml:mi></mml:math> package <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mi>submax</mml:mi></mml:math> which contains the NHANES example. An online Appendix provides simulation results and further analysis of the example.

Comparison of the Value of Nursing Work Environments in Hospitals Across Different Levels of Patient Risk

IMPORTANCE

The literature suggests that hospitals with better nursing work environments provide better quality of care. Less is known about value (cost vs quality).

OBJECTIVES

To test whether hospitals with better nursing work environments displayed better value than those with worse nursing environments and to determine patient risk groups associated with the greatest value.

DESIGN, SETTING, AND PARTICIPANTS

A retrospective matched-cohort design, comparing the outcomes and cost of patients at focal hospitals recognized nationally as having good nurse working environments and nurse-to-bed ratios of 1 or greater with patients at control group hospitals without such recognition and with nurse-to-bed ratios less than 1. This study included 25 752 elderly Medicare general surgery patients treated at focal hospitals and 62 882 patients treated at control hospitals during 2004-2006 in Illinois, New York, and Texas. The study was conducted between January 1, 2004, and November 30, 2006; this analysis was conducted from April to August 2015.

EXPOSURES

Focal vs control hospitals (better vs worse nursing environment).

MAIN OUTCOMES AND MEASURES

Thirty-day mortality and costs reflecting resource utilization.

RESULTS

This study was conducted at 35 focal hospitals (mean nurse-to-bed ratio, 1.51) and 293 control hospitals (mean nurse-to-bed ratio, 0.69). Focal hospitals were larger and more teaching and technology intensive than control hospitals. Thirty-day mortality in focal hospitals was 4.8% vs 5.8% in control hospitals (P < .001), while the cost per patient was similar: the focal-control was -$163 (95% CI = -$542 to $215; P = .40), suggesting better value in the focal group. For the focal vs control hospitals, the greatest mortality benefit (17.3% vs 19.9%; P < .001) occurred in patients in the highest risk quintile, with a nonsignificant cost difference of $941 per patient ($53 701 vs $52 760; P = .25). The greatest difference in value between focal and control hospitals appeared in patients in the second-highest risk quintile, with mortality of 4.2% vs 5.8% (P < .001), with a nonsignificant cost difference of -$862 ($33 513 vs $34 375; P = .12).

CONCLUSIONS AND RELEVANCE

Hospitals with better nursing environments and above-average staffing levels were associated with better value (lower mortality with similar costs) compared with hospitals without nursing environment recognition and with below-average staffing, especially for higher-risk patients. These results do not suggest that improving any specific hospital's nursing environment will necessarily improve its value, but they do show that patients undergoing general surgery at hospitals with better nursing environments generally receive care of higher value.

Comparing Outcomes between Antibody Induction Therapies in Kidney Transplantation

Kidney transplant recipients often receive antibody induction. Previous studies of induction therapy were often limited by short follow-up and/or absence of information about complications. After linking Organ Procurement and Transplantation Network data with Medicare claims, we compared outcomes between three induction therapies for kidney recipients. Using novel matching techniques developed on the basis of 15 clinical and demographic characteristics, we generated 1:1 pairs of alemtuzumab-rabbit antithymocyte globulin (rATG) (5330 pairs) and basiliximab-rATG (9378 pairs) recipients. We used paired Cox regression to analyze the primary outcomes of death and death or allograft failure. Secondary outcomes included death or sepsis, death or lymphoma, death or melanoma, and healthcare resource utilization within 1 year. Compared with rATG recipients, alemtuzumab recipients had higher risk of death (hazard ratio [HR], 1.14; 95% confidence interval [95% CI], 1.03 to 1.26; P<0.01) and death or allograft failure (HR, 1.18; 95% CI, 1.09 to 1.28; P<0.001). Results for death as well as death or allograft failure were generally consistent among elderly and nonelderly subgroups and among pairs receiving oral prednisone. Compared with rATG recipients, basiliximab recipients had higher risk of death (HR, 1.08; 95% CI, 1.01 to 1.16; P=0.03) and death or lymphoma (HR, 1.12; 95% CI, 1.01 to 1.23; P=0.03), although these differences were not confirmed in subgroup analyses. One-year resource utilization was slightly lower among alemtuzumab recipients than among rATG recipients, but did not differ between basiliximab and rATG recipients. This observational evidence indicates that, compared with alemtuzumab and basiliximab, rATG associates with lower risk of adverse outcomes, including mortality.

Outcomes, ICU Use, and Length of Stay in Chronically Ill Black and White Children on Medicaid and Hospitalized for Surgery

BACKGROUND

With increasing Medicaid coverage, it has become especially important to determine whether racial differences exist within the Medicaid system. We asked whether disparities exist in hospital practice and patient outcomes between matched black and white Medicaid children with chronic conditions undergoing surgery.

STUDY DESIGN

We conducted a matched cohort study, matching 6,398 pairs within states on detailed patient characteristics using data from 25 states contributing adequate Medicaid Analytic eXtract claims for admissions of children with chronic conditions undergoing the same surgical procedures between January 1, 2009 and November 30, 2010 for ages 1 to 18 years.

RESULTS

The black patient 30-day revisit rate was 19.3% vs 19.8% in matched white patients (p = 0.61), 30-day readmission rates were 7.0% vs 6.9% (p = 0.43), and 30-day mortality rates were 0.38% vs 0.19% (p = 0.06), respectively. A higher percentage of black patients exceeded their own state's individual median length of stay (44.0% vs 39.6%; p < 0.001) and median ICU length of stay (25.9% vs 23.8%; p < 0.001). Intensive care unit use was higher in black patients (25.9% vs 23.8%; p < 0.001). After adjusting for multiple testing, only 2 states were found to differ significantly by race (New York for length of stay and New Jersey for ICU use).

CONCLUSIONS

We did not observe disparities in 30-day revisits and readmissions for chronically ill children in Medicaid undergoing surgery, and only slight differences in length of stay, ICU length of stay, and use of the ICU, where blacks displayed somewhat elevated rates compared with white controls.

Racial Disparities in Medicaid Asthma Hospitalizations

BACKGROUND AND OBJECTIVES

Black children with asthma comprise one-third of all asthma patients in Medicaid. With increasing Medicaid coverage, it has become especially important to monitor Medicaid for differences in hospital practice and patient outcomes by race.

METHODS

A multivariate matched cohort design, studying 11 079 matched pairs of children in Medicaid (black versus white matched pairs from inside the same state) admitted for asthma between January 1, 2009 and November 30, 2010 in 33 states contributing adequate Medicaid Analytic eXtract claims.

RESULTS

Ten-day revisit rates were 3.8% in black patients versus 4.2% in white patients (P = .12); 30-day revisit and readmission rates were also not significantly different by race (10.5% in black patients versus 10.8% in white patients; P = .49). Length of stay (LOS) was also similar; both groups had a median stay of 2.0 days, with a slightly lower percentage of black patients exceeding their own state's median LOS (30.2% in black patients versus 31.8% in white patients; P = .01). The mean paired difference in LOS was 0.00 days (95% confidence interval, -0.08 to 0.08). However, ICU use was higher in black patients than white patients (22.2% versus 17.5%; P < .001). After adjusting for multiple testing, only 4 states were found to differ significantly, but only in ICU use, where blacks had higher rates of use.

CONCLUSIONS

For closely matched black and white patients, racial disparities concerning asthma admission outcomes and style of practice are small and generally nonsignificant, except for ICU use, where we observed higher rates in black patients.

Dropping out of High School in the United States: An Observational Study

Using data from a two-stage probability sample of U.S. high school students, an attempt is made to estimate the effect that dropping out has on cognitive achievement test scores. Each sampled dropout from a school is matched by a multivariate procedure to a student who remained in the same school. The matched pair differences are then adjusted using analysis of covariance. The possibility that important covariates have been omitted from the analysis is addressed through tests of ignorable treatment assignment and through sensitivity analyses.

An adaptive Mantel-Haenszel test for sensitivity analysis in observational studies

In a sensitivity analysis in an observational study with a binary outcome, is it better to use all of the data or to focus on subgroups that are expected to experience the largest treatment effects? The answer depends on features of the data that may be difficult to anticipate, a trade-off between unknown effect-sizes and known sample sizes. We propose a sensitivity analysis for an adaptive test similar to the Mantel-Haenszel test. The adaptive test performs two highly correlated analyses, one focused analysis using a subgroup, one combined analysis using all of the data, correcting for multiple testing using the joint distribution of the two test statistics. Because the two component tests are highly correlated, this correction for multiple testing is small compared with, for instance, the Bonferroni inequality. The test has the maximum design sensitivity of two component tests. A simulation evaluates the power of a sensitivity analysis using the adaptive test. Two examples are presented. An R package, sensitivity2x2xk, implements the procedure.